In [212]:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
%matplotlib inline
In [147]:
#reading the data set
shop=pd.read_csv(r"C:\Users\HP\Downloads\shopping_trends_updated.csv")
shop.shape
Out[147]:
(3900, 18)
In [149]:
shop.to_excel('shopping_trends_updated.xlsx')
shop.head()
Out[149]:
Customer ID Age Gender Item Purchased Category Purchase Amount (USD) Location Size Color Season Review Rating Subscription Status Shipping Type Discount Applied Promo Code Used Previous Purchases Payment Method Frequency of Purchases
0 1 55 Male Blouse Clothing 53 Kentucky L Gray Winter 3.1 Yes Express Yes Yes 14 Venmo Fortnightly
1 2 19 Male Sweater Clothing 64 Maine L Maroon Winter 3.1 Yes Express Yes Yes 2 Cash Fortnightly
2 3 50 Male Jeans Clothing 73 Massachusetts S Maroon Spring 3.1 Yes Free Shipping Yes Yes 23 Credit Card Weekly
3 4 21 Male Sandals Footwear 90 Rhode Island M Maroon Spring 3.5 Yes Next Day Air Yes Yes 49 PayPal Weekly
4 5 45 Male Blouse Clothing 49 Oregon M Turquoise Spring 2.7 Yes Free Shipping Yes Yes 31 PayPal Annually
In [32]:
#to find the data types in the data
shop.dtypes
Out[32]:
Customer ID                 int64
Age                         int64
Gender                     object
Item Purchased             object
Category                   object
Purchase Amount (USD)       int64
Location                   object
Size                       object
Color                      object
Season                     object
Review Rating             float64
Subscription Status        object
Shipping Type              object
Discount Applied           object
Promo Code Used            object
Previous Purchases          int64
Payment Method             object
Frequency of Purchases     object
dtype: object
In [36]:
#to find the data types in the data

shop.columns
Out[36]:
Index(['Customer ID', 'Age', 'Gender', 'Item Purchased', 'Category',
       'Purchase Amount (USD)', 'Location', 'Size', 'Color', 'Season',
       'Review Rating', 'Subscription Status', 'Shipping Type',
       'Discount Applied', 'Promo Code Used', 'Previous Purchases',
       'Payment Method', 'Frequency of Purchases'],
      dtype='object')
In [43]:
#to find the information about the data
shop.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3900 entries, 0 to 3899
Data columns (total 18 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Customer ID             3900 non-null   int64  
 1   Age                     3900 non-null   int64  
 2   Gender                  3900 non-null   object 
 3   Item Purchased          3900 non-null   object 
 4   Category                3900 non-null   object 
 5   Purchase Amount (USD)   3900 non-null   int64  
 6   Location                3900 non-null   object 
 7   Size                    3900 non-null   object 
 8   Color                   3900 non-null   object 
 9   Season                  3900 non-null   object 
 10  Review Rating           3900 non-null   float64
 11  Subscription Status     3900 non-null   object 
 12  Shipping Type           3900 non-null   object 
 13  Discount Applied        3900 non-null   object 
 14  Promo Code Used         3900 non-null   object 
 15  Previous Purchases      3900 non-null   int64  
 16  Payment Method          3900 non-null   object 
 17  Frequency of Purchases  3900 non-null   object 
dtypes: float64(1), int64(4), object(13)
memory usage: 548.6+ KB
In [45]:
shop.isnull().sum()
Out[45]:
Customer ID               0
Age                       0
Gender                    0
Item Purchased            0
Category                  0
Purchase Amount (USD)     0
Location                  0
Size                      0
Color                     0
Season                    0
Review Rating             0
Subscription Status       0
Shipping Type             0
Discount Applied          0
Promo Code Used           0
Previous Purchases        0
Payment Method            0
Frequency of Purchases    0
dtype: int64
In [11]:
shop.describe()
Out[11]:
Customer ID Age Purchase Amount (USD) Review Rating Previous Purchases
count 3900.000000 3900.000000 3900.000000 3900.000000 3900.000000
mean 1950.500000 44.068462 59.764359 3.749949 25.351538
std 1125.977353 15.207589 23.685392 0.716223 14.447125
min 1.000000 18.000000 20.000000 2.500000 1.000000
25% 975.750000 31.000000 39.000000 3.100000 13.000000
50% 1950.500000 44.000000 60.000000 3.700000 25.000000
75% 2925.250000 57.000000 81.000000 4.400000 38.000000
max 3900.000000 70.000000 100.000000 5.000000 50.000000
In [47]:
print(f"The unique values of the 'Gender' column are:{shop['Gender'].unique()}")
print()

The unique values of the 'Gender' column are:['Male' 'Female']
In [13]:
shop.describe(include="object")
Out[13]:
Gender Item Purchased Category Location Size Color Season Subscription Status Shipping Type Discount Applied Promo Code Used Payment Method Frequency of Purchases
count 3900 3900 3900 3900 3900 3900 3900 3900 3900 3900 3900 3900 3900
unique 2 25 4 50 4 25 4 2 6 2 2 6 7
top Male Blouse Clothing Montana M Olive Spring No Free Shipping No No PayPal Every 3 Months
freq 2652 171 1737 96 1755 177 999 2847 675 2223 2223 677 584
In [49]:
print(f"The unique values of the 'Category' column are:{shop['Category'].unique()}")
print()

The unique values of the 'Category' column are:['Clothing' 'Footwear' 'Outerwear' 'Accessories']
In [51]:
print(f"The unique values of the 'Size' column are:{shop['Size'].unique()}")
print()

The unique values of the 'Size' column are:['L' 'S' 'M' 'XL']
In [53]:
print(f"The unique values of the 'Subscription Status' column are:{shop['Subscription Status'].unique()}")
print()

The unique values of the 'Subscription Status' column are:['Yes' 'No']
In [55]:
print(f"The unique values of the 'Shipping Type' column are:{shop['Shipping Type'].unique()}")
print()

The unique values of the 'Shipping Type' column are:['Express' 'Free Shipping' 'Next Day Air' 'Standard' '2-Day Shipping'
 'Store Pickup']
In [57]:
print(f"The unique values of the 'Discount Applied' column are:{shop['Discount Applied'].unique()}")
print()

The unique values of the 'Discount Applied' column are:['Yes' 'No']
In [59]:
print(f"The unique values of the 'Promo Code Used' column are:{shop['Promo Code Used'].unique()}")
print()

The unique values of the 'Promo Code Used' column are:['Yes' 'No']
In [61]:
print(f"The unique values of the 'Payment Method' column are:{shop['Payment Method'].unique()}")
print()

The unique values of the 'Payment Method' column are:['Venmo' 'Cash' 'Credit Card' 'PayPal' 'Bank Transfer' 'Debit Card']
In [ ]:

OBSERVATION:¶

Upon initial examination of the dataset, it is evident that we have a comprehensive and well-structured dataset with 3900 rows and 18 columns. The data is complete, with no missing values, which allows us to proceed confidently with our analysis.

Let's delve into the columns and their significance in understanding our customers

Customer ID: This column serves as a unique identifier for each customer, enabling us to differentiate between individuals.

Age: The age column provides insights into the age demographics of our customers, helping us understand their preferences and behaviors.

Gender: This column showcases the gender of the customers, enabling us to analyze buying patterns based on gender.

Item Purchased: Here, we can identify the specific products that customers have bought, allowing us to gain an understanding of popular choices.

Category: The category column categorizes the products into different groups such as clothing, footwear, and more, aiding us in analyzing trends within specific product categories.

Purchase Amount (USD): This column reveals the amount customers spent on their purchases, providing insights into their spending habits.

Location: The location column indicates the geographical location of customers, which can help identify regional trends and preferences.

Size: This column denotes the size of the purchased products, assisting in understanding size preferences across different categories.

Color: Here, we can determine the color preferences of customers, aiding in analyzing color trends and their impact on purchasing decisions.

Season: The season column allows us to identify the season during which customers made their purchases, enabling us to explore seasonal shopping trends.

Review Rating: This column showcases the ratings given by customers, providing valuable feedback on product satisfaction and quality.

Subscription Status: This column indicates whether customers have opted for a subscription status, which can help us understand customer loyalty and engagement.

Shipping Type: Here, we can identify the different shipping methods used to deliver products to customers, shedding light on preferred shipping options.

Discount Applied: This column indicates whether a discount was applied to the purchased products, enabling us to analyze the impact of discounts on customer behavior.

Promo Code Used: Here, we can identify whether customers utilized promo codes during their purchases, helping us evaluate the effectiveness of promotional campaigns.

Previous Purchases: This column reveals the number of previous purchases made by customers, aiding in understanding customer loyalty and repeat business.

Payment Method: The payment method column showcases the various methods used by customers to make their purchases, allowing us to analyze preferred payment options.

Frequency of Purchases: This column provides insights into the frequency at which customers make purchases, helping us identify patterns and customer buying habits.

Customer buying habits. With this rich and diverse dataset, we are well-equipped to explore customer shopping trends, understand their preferences, and uncover valuable insights that can drive informed decision-making and enhance the overall customer experience. Let's embark on this exciting analysis journey!

In [ ]:

1.What is the overall distribution of customer ages in the dataset?¶

In [65]:
shop['Age'].value_counts()
Out[65]:
Age
69    88
57    87
41    86
25    85
49    84
50    83
54    83
27    83
62    83
32    82
19    81
58    81
42    80
43    79
28    79
31    79
37    77
46    76
29    76
68    75
59    75
63    75
56    74
36    74
55    73
52    73
64    73
35    72
51    72
65    72
40    72
45    72
47    71
66    71
30    71
23    71
38    70
53    70
18    69
21    69
26    69
34    68
48    68
24    68
39    68
70    67
22    66
61    65
60    65
33    63
20    62
67    54
44    51
Name: count, dtype: int64
In [67]:
shop['Age'].mean()
Out[67]:
44.06846153846154
In [151]:
shop['Age_Category']=pd.cut(shop['Age'],bins=[0, 15, 18, 30, 50, 70], labels=['child','teen', 'young Adults','Middle-Aged Adults','old'])
In [153]:
fig = px.histogram(shop, y='Age' , x='Age_Category')
fig.show()

'''Fig 1.Represents how different age groups (categories) are distributed based on age data.'''

2. How does the average purchase amount vary across different product categories?¶

In [91]:
shop.columns
Out[91]:
Index(['Customer ID', 'Age', 'Gender', 'Item Purchased', 'Category',
       'Purchase Amount (USD)', 'Location', 'Size', 'Color', 'Season',
       'Review Rating', 'Subscription Status', 'Shipping Type',
       'Discount Applied', 'Promo Code Used', 'Previous Purchases',
       'Payment Method', 'Frequency of Purchases', 'Age_Category'],
      dtype='object')
In [155]:
shop['Category'].unique()
Out[155]:
array(['Clothing', 'Footwear', 'Outerwear', 'Accessories'], dtype=object)
In [157]:
shop.groupby('Category')['Purchase Amount (USD)'].mean()
Out[157]:
Category
Accessories    59.838710
Clothing       60.025331
Footwear       60.255426
Outerwear      57.172840
Name: Purchase Amount (USD), dtype: float64

3.Which gender has the highest number of purchases?¶

In [159]:
sns.barplot(shop,x='Gender',y='Purchase Amount (USD)')
Out[159]:
<Axes: xlabel='Gender', ylabel='Purchase Amount (USD)'>
No description has been provided for this image

''' Fig2:Represents the highest no.of purchases based on gender'''

4. What are the most commonly purchased items in each category?¶

In [161]:
shop.groupby('Category')['Item Purchased'].value_counts()
Out[161]:
Category     Item Purchased
Accessories  Jewelry           171
             Belt              161
             Sunglasses        161
             Scarf             157
             Hat               154
             Handbag           153
             Backpack          143
             Gloves            140
Clothing     Blouse            171
             Pants             171
             Shirt             169
             Dress             166
             Sweater           164
             Socks             159
             Skirt             158
             Shorts            157
             Hoodie            151
             T-shirt           147
             Jeans             124
Footwear     Sandals           160
             Shoes             150
             Sneakers          145
             Boots             144
Outerwear    Jacket            163
             Coat              161
Name: count, dtype: int64
In [165]:
fig=px.histogram(shop,x='Item Purchased',color='Category')
fig.show()

Fig3.Represents the distribution of items purchased, categorized by different groups.

In [ ]:

5. Are there any specific seasons or months where customer spending is significantly higher?¶

In [115]:
shop['Season'].unique()
Out[115]:
array(['Winter', 'Spring', 'Summer', 'Fall'], dtype=object)
In [21]:
shop['Season'].value_counts()
Out[21]:
Season
Spring    999
Fall      975
Winter    971
Summer    955
Name: count, dtype: int64
In [23]:
fig=px.histogram(shop,x='Season' ,range_y=[800,1200])
fig.show()

Fig4.Represents possibly sales are distributed across different seasons

In [ ]:

6.What is the average rating given by customers for each product category?¶

In [27]:
shop.groupby('Category')['Review Rating'].mean()
Out[27]:
Category
Accessories    3.768629
Clothing       3.723143
Footwear       3.790651
Outerwear      3.746914
Name: Review Rating, dtype: float64
In [43]:
shop_groupby = shop.groupby('Category')['Review Rating'].mean().reset_index()
print(shop_groupby)

      Category  Review Rating
0  Accessories       3.768629
1     Clothing       3.723143
2     Footwear       3.790651
3    Outerwear       3.746914
In [48]:
fig = px.bar(shop_groupby ,x= 'Category' , y = 'Review Rating' )
fig.show()

Fig5 Represents average rating given by customers for each product category

In [ ]:

7 Are there any notable differences in purchase behavior between subscribed and non-subscribed customers?¶

In [61]:
shop.columns
Out[61]:
Index(['Customer ID', 'Age', 'Gender', 'Item Purchased', 'Category',
       'Purchase Amount (USD)', 'Location', 'Size', 'Color', 'Season',
       'Review Rating', 'Subscription Status', 'Shipping Type',
       'Discount Applied', 'Promo Code Used', 'Previous Purchases',
       'Payment Method', 'Frequency of Purchases'],
      dtype='object')
In [63]:
shop['Subscription Status'].value_counts()
Out[63]:
Subscription Status
No     2847
Yes    1053
Name: count, dtype: int64
In [71]:
sns.barplot(shop  , x = 'Subscription Status' , y = 'Purchase Amount (USD)')
Out[71]:
<Axes: xlabel='Subscription Status', ylabel='Purchase Amount (USD)'>
No description has been provided for this image

Fig6:Represents how purchase amounts (in USD) vary based on different subscription statuses

In [75]:
shop.groupby('Subscription Status')['Purchase Amount (USD)'].mean()
Out[75]:
Subscription Status
No     59.865121
Yes    59.491928
Name: Purchase Amount (USD), dtype: float64
In [ ]:

8 Which payment method is the most popular among customers?¶

In [80]:
shop.groupby('Payment Method')['Purchase Amount (USD)'].mean().sort_values(ascending= True)
Out[80]:
Payment Method
Venmo            58.949527
PayPal           59.245199
Cash             59.704478
Bank Transfer    59.712418
Credit Card      60.074516
Debit Card       60.915094
Name: Purchase Amount (USD), dtype: float64
In [82]:
sns.barplot(shop ,x='Payment Method' , y = 'Purchase Amount (USD)')
plt.show()
No description has been provided for this image

Fig7 Represents Most Popular Payment Method among Customers

In [ ]:

9 Do customers who use promo codes tend to spend more than those who don't?¶

In [95]:
shop_groupby=shop.groupby('Promo Code Used')['Purchase Amount (USD)'].sum().reset_index()
In [93]:
fig = px.sunburst(shop , path=['Gender' , 'Promo Code Used'] , values='Purchase Amount (USD)')
fig.show()
In [ ]:
In [97]:
fig  =  px.bar(shop_groupby , x= 'Promo Code Used' , y = 'Purchase Amount (USD)')
fig.show()

Fig8:Represents who use promo codes tend to spend more than those who don't.

In [ ]:

10 How does the frequency of purchases vary across different age groups?¶

In [45]:
shop['Age_Category'].unique()
Out[45]:
['old', 'young Adults', 'Middle-Aged Adults', 'teen']
Categories (5, object): ['child' < 'teen' < 'young Adults' < 'Middle-Aged Adults' < 'old']
In [47]:
shop_group = shop.groupby('Frequency of Purchases')['Age'].sum()
In [49]:
px.sunburst(shop , path=['Frequency of Purchases','Age_Category'] , values='Age')

C:\Users\HP\anaconda3\Lib\site-packages\plotly\express\_core.py:1706: FutureWarning:

The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.

11 Are there any correlations between the size of the product and the purchase amount?¶

In [58]:
shop_group = shop.groupby('Size')['Purchase Amount (USD)'].sum().reset_index()
In [60]:
fig  = px.bar(shop_group , x = 'Size' , y ='Purchase Amount (USD)'  )
fig.show()

Fig9:Represents correlations between the size of the product and the purchase amount

12 Which shipping type is preferred by customers for different product categories?¶

In [65]:
shop.groupby('Category')['Shipping Type'].value_counts().sort_values(ascending= False)
Out[65]:
Category     Shipping Type 
Clothing     Standard          297
             Free Shipping     294
             Next Day Air      293
             Express           290
             Store Pickup      282
             2-Day Shipping    281
Accessories  Store Pickup      217
             Next Day Air      211
             Standard          208
             2-Day Shipping    206
             Express           203
             Free Shipping     195
Footwear     Free Shipping     122
             Standard          100
             Store Pickup       98
             Express            96
             Next Day Air       93
             2-Day Shipping     90
Outerwear    Free Shipping      64
             Express            57
             Store Pickup       53
             Next Day Air       51
             2-Day Shipping     50
             Standard           49
Name: count, dtype: int64
In [ ]:

13 How does the presence of a discount affect the purchase decision of customers?¶

In [70]:
shop_group = shop.groupby('Discount Applied')['Purchase Amount (USD)'].sum().reset_index()
In [72]:
px.histogram(shop_group , x = 'Discount Applied' , y = 'Purchase Amount (USD)')

Fig10:Represents the presence of a discount affect the purchase decision of customers?

In [ ]:

14 Are there any specific colors that are more popular among customers?¶

In [76]:
shop['Color'].value_counts().nlargest(5)
Out[76]:
Color
Olive     177
Yellow    174
Silver    173
Teal      172
Green     169
Name: count, dtype: int64
In [78]:
px.histogram(shop , x = 'Color')

Fig11:Represents specific colors that are more popular among customers

In [ ]:

15 What is the average number of previous purchases made by customers?¶

In [83]:
shop['Previous Purchases'].mean()
Out[83]:
25.35153846153846

16 Are there any noticeable differences in purchase behavior between different locations?¶

In [90]:
shop.groupby('Location')['Purchase Amount (USD)'].mean().sort_values(ascending = True)
Out[90]:
Location
Connecticut       54.179487
Kansas            54.555556
Delaware          55.325581
Kentucky          55.721519
Maryland          55.755814
Florida           55.852941
Wisconsin         55.946667
Colorado          56.293333
Minnesota         56.556818
New Jersey        56.746269
Maine             56.987013
Vermont           57.176471
Oregon            57.337838
Louisiana         57.714286
Hawaii            57.723077
Missouri          57.913580
Oklahoma          58.346667
South Carolina    58.407895
Georgia           58.797468
Indiana           58.924051
California        59.000000
Alabama           59.112360
New Hampshire     59.422535
Nebraska          59.448276
Idaho             60.075269
Montana           60.250000
Ohio              60.376623
New York          60.425287
South Dakota      60.514286
Wyoming           60.690141
North Carolina    60.794872
Iowa              60.884058
Massachusetts     60.888889
Mississippi       61.037500
Illinois          61.054348
Arkansas          61.113924
Texas             61.194805
Rhode Island      61.444444
New Mexico        61.901235
Tennessee         61.974026
Michigan          62.095890
Utah              62.577465
Virginia          62.883117
North Dakota      62.891566
Washington        63.328767
Nevada            63.379310
West Virginia     63.876543
Arizona           66.553846
Pennsylvania      66.567568
Alaska            67.597222
Name: Purchase Amount (USD), dtype: float64
In [96]:
fig = px.bar(shop, x = 'Location' , y = 'Purchase Amount (USD)')
fig.show()

Fig12:Represents there any noticeable differences in purchase behavior between different locations

17 Is there a relationship between customer age and the category of products they purchase?¶

In [175]:
shop_group = shop.groupby('Category')['Age'].mean().reset_index()
In [177]:
fig = px.bar(shop_group ,y = 'Age' , x= 'Category')
fig.show()

Fig13:Represents a relationship between customer age and the category of products they purchase

In [ ]:

18 How does the average purchase amount differ between male and female customers?¶

In [189]:
shop_group = shop.groupby('Gender')['Purchase Amount (USD)'].sum().reset_index()
In [199]:
fig = px.bar(shop_group ,y = 'Purchase Amount (USD)' , x= 'Gender')
fig.show()

Fig14:Represents the average purchase amount differ between male and female customers

In [ ]:
In [ ]:
In [ ]: